background-color: #006DAE class: middle center hide-slide-number <div class="shade_black" style="width:60%;right:0;bottom:0;padding:10px;border: dashed 4px white;margin: auto;"> <i class="fas fa-exclamation-circle"></i> These slides are viewed best by Chrome and occasionally need to be refreshed if elements did not load properly. </div> <br> .white[Press the **right arrow** to progress to the next slide!] --- background-image: url(images/Werombi_Bushfire.jpg) background-size: cover class: hide-slide-number split-70 title-slide count: false .column.shade_black[.content[ <br> # .monash-blue.outline-text[Using Remote Sensing Data to Understand Fire Ignition Risk in Victoria] <h2 class="monash-blue2 outline-text" style="font-size: 30pt!important;"></h2> <br> <h2 style="font-weight:900!important;"></h2> .bottom_abs.width100[ *Helen Evangelista, Brenwin Ang, Di Cook, Emily Dodwell, Chris Volinsky, Weihao Li*
<i class="fas fa-link faa-float animated "></i>
[https://numbats/bushyr](https://numbats/bushyr) ACEMS Retreat, Nov 3 2021 <br> ] ]] <div class="column transition monash-m-new delay-1s" style="clip-path:url(#swipe__clip-path);"> <div class="background-image" style="background-image:url('images/large.png');background-position: center;background-size:cover;margin-left:3px;"> <svg class="clip-svg absolute"> <defs> <clipPath id="swipe__clip-path" clipPathUnits="objectBoundingBox"> <polygon points="0.5745 0, 0.5 0.33, 0.42 0, 0 0, 0 1, 0.27 1, 0.27 0.59, 0.37 1, 0.634 1, 0.736 0.59, 0.736 1, 1 1, 1 0, 0.5745 0" /> </clipPath> </defs> </svg> </div> </div> --- # IDEAS Challenge *Motivation*: The collaboration would develop risk models and visualisations, to monitor potential fire ignitions and track fires from satellite hotspots, in real-time, for the 2021-2022 Victorian bushfire season. These will be made these publicly available by extending the existing web app. *Team*: - Helen Evangelista, Monash Master of Business Analytics - Brenwin Ang, Monash Master of Business Analytics - Prof Di Cook, EBS, Monash - Emily Dodwell, AT&T - Chris Volinsky, AT&T - Weihao (Patrick) Li, EBS, Monash, PhD student --- # 🗺 Background: Patrick's Honours research 1. .monash-blue2[Algorithm] to detect bushfire ignition from hotspot data, published in R package `spotoroo` and upcoming R Journal article. 2. .monash-blue2[Model to predict the cause] of bushfire ignition, using historical data, and metadata, temperature, precipitation, winds, radiation, vegetation/fuel layer, roads, recreation sites, CFA stations. 3. Prediction of the .monash-blue2[causes of the 2019-2020] Victorian bushfires 4. A .monash-blue2[complete and adaptable workflow] for monitoring and understanding new ignitions from hotspot data. 5. **.monash-orange2[Shiny app] for exploration of historical fire origins, predicted causes of 2019-2020 fires and .monash-orange2[future fire risk maps].** 6. All work conducted with .monash-blue2[open data and open source software]. --- # Shiny app: https://ebsmonash.shinyapps.io/VICfire/ <iframe src="https://ebsmonash.shinyapps.io/VICfire/?showcase=0" width="110%" height="550px" data-external="1"></iframe> --- # Data sources update - Remote sensing `\(^a\)` data 📡 for all seasons (2016/2017-2020/2021) .monash-blue2[clustered to identify fire ignition] spots. - Historical fire origins 🔥 for 2019/2020: can .monash-blue2[compare] our predictions for that season now. - Metadata 🌦️🌿⛺: updated and expanded for all seasons - [SILO](https://www.longpaddock.qld.gov.au/silo/): max_temp, rh, radiation, et_short_crop, daily_rain - [ERA5 Reanalysis data](https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-single-levels-monthly-means?tab=overview): lai_hv, lai_lv, WS10 - [BoM’s AWRA-L](http://www.bom.gov.au/water/landscape/#/sm/Actual/month/-26.32/132.54/3/Point/Separate/-15.6/130.25/2021/4/30/): s0_pct - [DELWP](https://discover.data.vic.gov.au/dataset/forest-types-of-victoria): forest cover <br> `\(^a\)` Japan Aerospace Exploration Agency provides a hotspot product (reflected energy from the earth) taken from the **Himawari-8** satellite. --- # 📐 Modelling risk .pull-left[ - Hotspots (2016-2021)more reliable for locating fire ignitions, especially in remote locations than the first responder fire origins - Proportion of fire ignitions in spatial grid computed, for each season - Metadata, including lag variabes, used to model proportions, using random forest (GLM and lasso) .monash-gray50[Grid spatially] ] .pull-right.wider[
] --- count: false # 📐 Modelling risk .pull-left[ - Hotspots (2016-2021)more reliable for locating fire ignitions, especially in remote locations than the first responder fire origins - Proportion of fire ignitions in spatial grid computed, for each season - Metadata, including lag variabes, used to model proportions, using random forest (GLM and lasso) .monash-gray50[2016-2017] ] .pull-right.wider[
] --- count: false # 📐 Modelling risk .pull-left[ - Hotspots (2016-2021)more reliable for locating fire ignitions, especially in remote locations than the first responder fire origins - Proportion of fire ignitions in spatial grid computed, for each season - Metadata, including lag variabes, used to model proportions, using random forest (GLM and lasso) .monash-gray50[2017-2018] ] .pull-right.wider[
] --- count: false # 📐 Modelling risk .pull-left[ - Hotspots (2016-2021)more reliable for locating fire ignitions, especially in remote locations than the first responder fire origins - Proportion of fire ignitions in spatial grid computed, for each season - Metadata, including lag variabes, used to model proportions, using random forest (GLM and lasso) .monash-gray50[2018-2019] ] .pull-right.wider[
] --- count: false # 📐 Modelling risk .pull-left[ - Hotspots (2016-2021)more reliable for locating fire ignitions, especially in remote locations than the first responder fire origins - Proportion of fire ignitions in spatial grid computed, for each season - Metadata, including lag variabes, used to model proportions, using random forest (GLM and lasso) .monash-gray50[2019-2020] ] .pull-right.wider[
] --- count: false # 📐 Modelling risk .pull-left[ - Hotspots (2016-2021)more reliable for locating fire ignitions, especially in remote locations than the first responder fire origins - Proportion of fire ignitions in spatial grid computed, for each season - Metadata, including lag variabes, used to model proportions, using random forest (GLM and lasso) .monash-gray50[2020-2021] ] .pull-right.wider[
] --- background-image: url(images/shiny_plan.png) background-size: 80% # 🔭 Plan for completion: shiny app --- # AT&T Collaboration <div align="center"> <video width="960" height="720" controls> <source src="ACEMS-ATT-Take1.mp4" type="video/mp4"> </video> </div> --- count: false # Relevance to Telecommunications Industry - Extreme weather and climate-related events pose significant risks to cellular network infrastructure, e.g.: + "Wildfire threat: Bay Area cell phone, internet service could go out, too" (*San Francisco Chronicle* - August 20, 2020) + "911 calls after Ida went unanswered in New Orleans due to ‘antiquated’ technology" (*The Washington Post* - August 30, 2021) - Necessary for telecom providers to address impact of climate perils including wind, flood, and fire on customer connectivity --- # Benefits of Collaboration to AT&T - As the severity of climate disasters are expected to increase, AT&T is committed to staying ahead of these dangers: + Developed *Climate Change Analysis Tool* with the US Department of Energy's Argonne National Laboratory + Published a white paper entitled *The Road to Climate Resiliency* * ACEMS research collaboration to predict wildfire risk is aligned with AT&T's climate resiliency efforts * Development of tools and methods for analytics and visualization of wildfire incidence are generalizable and extendable to other geographies --- background-image: url(images/Werombi_Bushfire.jpg) background-size: cover class: hide-slide-number split-70 count: false .column.shade_black[.content[ <br><br> ## Acknowledgements Slides produced using [Rmarkdown](https://github.com/rstudio/rmarkdown) with [xaringan](https://github.com/yihui/xaringan) styling. Monash style by the kunoichi, Dr Emi Tanaka. `spotoroo` package is available on CRAN and [Patrick's GitHub repo](https://github.com/TengMCing/spotoroo). Current developments are available at [bushyr GitHub repo](https://github.com/numbats/bushyr). # Thanks for listening! <br> <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" /></a><br />This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>. ]] <div class="column transition monash-m-new delay-1s" style="clip-path:url(#swipe__clip-path);"> <div class="background-image" style="background-image:url('images/large.png');background-position: center;background-size:cover;margin-left:3px;"> <svg class="clip-svg absolute"> <defs> <clipPath id="swipe__clip-path" clipPathUnits="objectBoundingBox"> <polygon points="0.5745 0, 0.5 0.33, 0.42 0, 0 0, 0 1, 0.27 1, 0.27 0.59, 0.37 1, 0.634 1, 0.736 0.59, 0.736 1, 1 1, 1 0, 0.5745 0" /> </clipPath> </defs> </svg> </div> </div>